Yolov5调整空间金字塔池化SPPCSPC/上采样方式bilinear-Toy模板网

这篇具有很好参考价值的文章主要介绍了Yolov5调整空间金字塔池化SPPCSPC/上采样方式bilinear。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

一、空间金字塔池化

SPP

sppcspc,python,深度学习,人工智能,cnn,计算机视觉

#   SPP结构，利用不同大小的池化核进行池化 5*5 9*9 13*13
#   先构建kernel_size=5, stride=1, padding=2的最大池化层
#   再构建kernel_size=9, stride=1, padding=4的最大池化层
#   再构建kernel_size=13, stride=1, padding=6的最大池化层
#   池化后堆叠
#---------------------------------------------------#
class SpatialPyramidPooling(nn.Module):
    def __init__(self, pool_sizes=[5, 9, 13]):
        super(SpatialPyramidPooling, self).__init__()
 
        self.maxpools = nn.ModuleList([nn.MaxPool2d(kernel_size=pool_size, stride=1, padding=pool_size//2) for pool_size in pool_sizes])
 
    def forward(self, x):
        features = [maxpool(x) for maxpool in self.maxpools[::-1]]
        features = torch.cat(features + [x], dim=1) # x指的是未经过最大池化的层
 
        return features

SPPF

sppcspc,python,深度学习,人工智能,cnn,计算机视觉

class SPPF(nn.Module):
    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
 
    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

SPPCSPC

sppcspc,python,深度学习,人工智能,cnn,计算机视觉

class SPPCSPC(nn.Module):
    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
        super(SPPCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))